Two-dimensional image component segmentation method based on improved DeepLab, and application

Abstract

The invention relates to a two-dimensional image component segmentation method based on improved DeepLab, and an application. The two-dimensional image component segmentation method carries out component segmentation on an acquired two-dimensional image through an improved DeepLab network, wherein the improved DeepLab network comprises an encoder and a jumping type decoder, and the encoder comprises a multi-convolution layer unit and a multi-scale self-adaptive morphological feature extraction unit, and the multi-scale self-adaptive morphological feature extraction unit is connected with the output end of the multi-convolution layer unit, and the jumping type decoder obtains deep features and shallow features at the same time, and the shallow features are obtained by an intermediate layerof the multi-convolution layer unit. Compared with the prior art, the two-dimensional image component segmentation method has the advantages of high adaptability, clear segmentation structure edges and the like.

Description

technical field [0001] The invention relates to image processing, in particular to a method and application of two-dimensional image component segmentation based on improved DeepLab. Background technique [0002] Part segmentation of two-dimensional images has good application prospects in automatic driving, medical image processing, drone applications, aerospace technology, etc. Different from the semantic segmentation that performs pixel labeling according to the object category in the figure, component segmentation is to further divide the pixels belonging to an object into different components of the object. [0003] In the research of image semantic segmentation, the emergence of convolutional neural network (Convolutional Neural Network, CNN) with powerful feature learning ability has greatly promoted its development. Practice has proved that convolutional neural network is more suitable for learning and expressing image features than traditional methods. . [0004] ...

AI Technical Summary

Problems solved by technology

[0005]Currently, most of the part segmentation algorithms based on convolutional neural network are designed for human body segmentation. The frame improves the segmentation accuracy, but the network framework is complex and the transferability is poor

Images